3D Point Cloud-Based Indoor Mobile Robot in 6-DoF Pose Localization Using a Wi-Fi-Aided Localization System

Mingcong Shu,Guoliang Chen,Zhenghua Zhang

doi:10.1109/access.2021.3060760

Mingcong Shu, Guoliang Chen + Show 1 more

Open Access

https://doi.org/10.1109/access.2021.3060760

Copy DOI

Abstract

Six-DoF (Six-degree-of-freedom) pose localization based on 3D point clouds is a challenging task for LBSs (localization-based services). This paper proposes a robust and efficient method that uses multimodal information (vision and Wi-Fi signal information) to estimate the 6-DoF pose of an RGBD camera on a robot with respect to complex 3D textured models of the indoor environment that can contain more than 650,000,000 points. Our developed method narrows the search scope, which delimits boundaries initially using the Wi-Fi location system and applies an environment-adaptive approach to determine the radius of the search sphere based on the signal stability of the Wi-Fi location system. In addition, we propose an algorithm for estimating a novel correspondence between local points with a 3D submap by combining 3D points and surface normals to acquire absolute poses from noisy and outlier-contaminated matching point sets for RGBD sensors in dynamic indoor scenes. Then, a novel two-level spatial verification strategy is used to estimate an accurate pose, which includes the use of a RANSAC (Random Sample Consensus) algorithm for identification and a direct least-square method to acquire the pose from the inliers. The proposed method has been implemented and tested extensively in various indoor scenes. The experimental results demonstrate that the Wi-Fi-aided localization system can efficiently localize a mobile robot in a variety of large-scale 3D point cloud datasets to realize stable time consumption and similar performance to state-of-the-art methods.

Highlights

Autonomous navigation and localization inside a building are essential capabilities of robotic intelligent systems [1, 2]
Real-case experiments in large-scale indoor scenes and the results of various state-ofthe-art methods demonstrate that the Wi-Fi-aided image-based localization system realized higher accuracy, stability and efficiency than four previously established algorithms
The proposed Wi-Fi-aid image-based localization algorithm for 6-DoF pose estimation with an RGBD camera and a wireless signal receiver placed on a robot has four innovative aspects: 1) To the best of our knowledge, we are the first to deeply apply a Wi-Fi location algorithm to the image-based localization process for 6-DoF pose estimation using an RGBD camera and a Wi-Fi receiver in a large-scale indoor environment that includes various complex scenes, which can inspire researchers in the same field to develop an elegant solution to the image-based localization problem

Summary

INTRODUCTION

Autonomous navigation and localization inside a building are essential capabilities of robotic intelligent systems [1, 2]. These topological approaches rely on visual feature landmarks that depend on the path of image capture beforehand, and this method does not satisfy our requirements since it relies on a metric map constructed from 2D image features To overcome this problem, we built a large-scale indoor 3D map and adapted a coarse-to-fine strategy that aided the Wi-Fi localization system in quickly estimating the RGBD camera’s 6-DoF pose of the robot with high accuracy. To build the indoor fingerprint efficiently and use highaccuracy location information in the vision localization system, we propose a vision-based radio map construction model that utilizes an external Wi-Fi receptor fixed on the robot and a built-in RGBD camera to collect visual information and Wi-.

Submap acquisition using Wi-Fi-aided positioning

EXPERIMENTAL VERIFICATION

Findings

CONCLUSIONS